Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication in Codenames
This addresses cross-cultural communication issues in AI-human or AI-AI interactions, but it is incremental as it builds on existing pragmatic reasoning frameworks.
The paper tackled the problem of cross-cultural communication failures in collaborative games by developing RSA+C3, a method that improved collaboration between simulated players of different cultures in Codenames Duet, showing successful inference of sociocultural context.
Cultural differences in common ground may result in pragmatic failure and misunderstandings during communication. We develop our method Rational Speech Acts for Cross-Cultural Communication (RSA+C3) to resolve cross-cultural differences in common ground. To measure the success of our method, we study RSA+C3 in the collaborative referential game of Codenames Duet and show that our method successfully improves collaboration between simulated players of different cultures. Our contributions are threefold: (1) creating Codenames players using contrastive learning of an embedding space and LLM prompting that are aligned with human patterns of play, (2) studying culturally induced differences in common ground reflected in our trained models, and (3) demonstrating that our method RSA+C3 can ease cross-cultural communication in gameplay by inferring sociocultural context from interaction. Our code is publicly available at github.com/icwhite/codenames.